Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4004 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4134. Min Range: -1.4134

Max Act: 1.4134. Min Act: -0.0000

Data Index: 518054 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 1.4134. Min Range: -1.4134

Max Act: 1.0761. Min Act: 0.0000

Data Index: 54368 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.9484. Min Act: -0.0000

Data Index: 610926 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.9493. Min Act: -0.0000

Data Index: 540187 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.9336. Min Act: -0.0000

Data Index: 862596 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1157552 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.8472. Min Act: -0.0000

Data Index: 625221 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.8807. Min Act: -0.0000

Data Index: 734347 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.8775. Min Act: -0.0000

Data Index: 233259 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.8812. Min Act: -0.0000

Data Index: 228277 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.9966. Min Act: -0.0000

Data Index: 123308 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.8184. Min Act: -0.0000

Data Index: 945088 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1235179 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.8321. Min Act: -0.0000

Data Index: 540748 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1133142 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.8135. Min Act: -0.0000

Data Index: 387840 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.7392. Min Act: -0.0000

Data Index: 740694 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1193616 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.7525. Min Act: -0.0000

Data Index: 222951 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 1.4134. Min Range: -1.4134

Max Act: 0.7398. Min Act: -0.0000

Data Index: 451594 (C4 (Web Text))

Max Activating Token Index: 258